There is a newer version of the record available.

Published December 6, 2020 | Version v9.0
Software Open

ultralytics/yolov3: v9.0 - YOLOv5 Forward Compatibility Release

  • 1. @ultralytics
  • 2. MarkAny
  • 3. State Grid Electric Power Research Institute
  • 4. University of Wisconsin-Madison
  • 5. Image Algorigthm Engineer
  • 6. @silverpond
  • 7. Scalar Research
  • 8. Elvees NeoTek JSC elveesneotek.ru
  • 9. NCTU College of AI
  • 10. Continental
  • 11. Infocusp
  • 12. Duke Applied Machine Laboratory
  • 13. Ritsumeikan University
  • 14. Polytechnique Montréal
  • 15. @VirtusLab
  • 16. Sandia National Laboratories

Description

This release is a major update to the https://github.com/ultralytics/yolov3 repository that brings forward-compatibility with YOLOv5, and incorporates numerous bug fixes, feature additions and performance improvements from https://github.com/ultralytics/yolov5 to this repo.

Branch Notice

The ultralytics/yolov3 repository is now divided into two branches:

  • Master branch: Forward-compatible with all YOLOv5 models and methods (recommended).
    $ git clone https://github.com/ultralytics/yolov3  # master branch (default)
    
  • Archive branch: Backwards-compatible with original darknet *.cfg models (⚠️ no longer maintained).
    $ git clone -b archive https://github.com/ultralytics/yolov3  # archive branch
    

<img src="https://user-images.githubusercontent.com/26833433/100382066-c8bc5200-301a-11eb-907b-799a0301595e.png" width="1000">** GPU Speed measures end-to-end time per image averaged over 5000 COCO val2017 images using a V100 GPU with batch size 32, and includes image preprocessing, PyTorch FP16 inference, postprocessing and NMS. EfficientDet data from google/automl at batch size 8.

Pretrained Checkpoints Model AP<sup>val</sup> AP<sup>test</sup> AP<sub>50</sub> Speed<sub>GPU</sub> FPS<sub>GPU</sub> params FLOPS YOLOv3 43.3 43.3 63.0 4.8ms 208 61.9M 156.4B YOLOv3-SPP 44.3 44.3 64.6 4.9ms 204 63.0M 157.0B YOLOv3-tiny 17.6 34.9 34.9 1.7ms 588 8.9M 13.3B

AP<sup>test</sup> denotes COCO test-dev2017 server results, all other AP results denote val2017 accuracy. All AP numbers are for single-model single-scale without ensemble or TTA. Reproduce mAP by python test.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65
Speed<sub>GPU</sub> averaged over 5000 COCO val2017 images using a GCP n1-standard-16 V100 instance, and includes image preprocessing, FP16 inference, postprocessing and NMS. NMS is 1-2ms/img. Reproduce speed by python test.py --data coco.yaml --img 640 --conf 0.25 --iou 0.45 All checkpoints are trained to 300 epochs with default settings and hyperparameters (no autoaugmentation). Test Time Augmentation (TTA) runs at 3 image sizes. Reproduce TTA** by python test.py --data coco.yaml --img 832 --iou 0.65 --augment

Requirements

Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install run:

$ pip install -r requirements.txt

Files

ultralytics/yolov3-v9.0.zip

Files (1.0 MB)

Name Size Download all
md5:4d905121b432448a6614c9cc27acd50c
1.0 MB Preview Download

Additional details

Related works